Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenCode – Open source AI coding agent

opencode.ai

Post reply on HN
Print view View original

411–420 of 700 posts

Re: OpenCode – Open source AI coding agent

#411

Post by embedding-shape »

girvo wrote: post #245
01100011 wrote: post #220

Stupid question, but are there models worth using that specialize in a particular programming language? For instance, I'd love to be able to run a local model on my GPU that is specific to C/C++ or Python. If such a thing exists, is it worth it vs one of the cloud-based frontier models? I'm guessing that a model which only covers a single language might be more compact and efficient vs a model trained across many lan…

I'm currently experimenting with (trying to) fine tune Qwen3.5 to make it better at a given language (Nim in this case); but I am quite bad at this, and honestly am unsure if it's even really fully feasible at the scale I have access to. Certainly been fun so far though, and I have a little Asus GX10 box on the way to experiment some more!

Been playing around with fine-tuning models for specific languages as well (Clojure and Rust mostly), but the persistent problem is high quality data sets, mostly I've been generating my own based on my own repositories and chat sessions, what approach are you taking for gathering the data?

Re: OpenCode – Open source AI coding agent

#412

Post by baq »

usagisushi wrote: post #321
staticassertion wrote: post #296

Earlier quoted context omitted.

> our constant claims that quality and security matter I'm 13 years into this industry, this is the first I'm hearing of this.

I’ve heard the "S" in IoT stands for Security.

same with openclaw

Re: OpenCode – Open source AI coding agent

#413

Post by embedding-shape »

madduci wrote: post #302

Have they "squatted" the name? It's the same name for the digital Sovereignty initiative in Germany https://opencode.de/

If it was a somewhat unique name, then yeah maybe. But "opencode" is probably as generic as you could make it, hard to claim to be "squatting" something so well used already... Earliest project on GitHub named "opencode" seems to date back to 2010, but I'm sure there are even earlier projects too: https://github.com/search?q=opencode&type=repositories&s=upd...

Re: OpenCode – Open source AI coding agent

#414

Post by knocte »

bjackman wrote: post #388
logicprog wrote: post #107

OpenCode was the first open source agent I used, and my main workhorse after experimenting briefly with Claude Code and realizing the potential of agentic coding. Due to that, and because it's a popular an open source alternative, I want to be able to recommend it and be enthusiastic about it. The problem for me is that the development practices of the people that are working on it are suboptimal at best; they're con…

That is very disappointing coz I've been wanting to try an alternative to Gemini CLI for exactly these reasons. The AI is great but the actual software is a buggy, slow, bloated blob of TypeScript (on a custom Node runtime IIUC!) that I really hate running. It takes multiple seconds to start, requires restarting to apply settings, constantly fucks up the terminal, often crashes due to JS heap overflows, doesn't respe…

> Is Claude Code like this too? I wonder if Pi is any better.

I'm very happy with Pi myself (running it on a small VPS so that I don't need to do sandboxing shenanigans).

Re: OpenCode – Open source AI coding agent

#415

Post by NicuCalcea »

pixelmelt wrote: post #80
Gigachad wrote: post #66

Earlier quoted context omitted.

Probably vibe coded

Some of the more recent versions of it had memory leaks so you couldn't just leave it on in the background

I had to abandon it because of the memory leak, it would fill up all my memory in a matter of minutes. The devs don't seem to pay it much attention: https://github.com/anomalyco/opencode/issues/5363

Re: OpenCode – Open source AI coding agent

#416

Post by kasey_junk »

KronisLV wrote: post #362
anonym29 wrote: post #63

Earlier quoted context omitted.

>or perhaps to route certain requests to Haiku or Sonnet instead of using Opus for everything, to cut down on the compute You can point Claude Code at a local inference server (e.g. llama.cpp, vLLM) and see which model names it sends each request to. It's not hard to do a MITM against it either. Claude Code does send some requests to Haiku, but not the ones you're making with whatever model you have it set to - these…

Sounds pretty sane, the same way how OpenWebUI and probably other software out there also has a concept of “tool models”, something you use for all the lower priority stuff. Actually curious to hear what others think about why Anthropic is so set on disallowing 3rd party tools on subscriptions.

The sota models are largely undifferentiated from each other in performance right now. And it’s possible open weight models will get “good enough” relatively soonish. This creates a classic case where inference becomes a commodity. Commodities have very low margins. Training puts them in an economic hole where low margins will kill them.

So they have to move up the stack to higher margin business solutions. Which is why they offer subsidized subscription plans in the first place. It’s a marketing cost. But they want those marketing dollars to drive up the stack not commodity inference use cases.

Re: OpenCode – Open source AI coding agent

#417

Post by dominotw »

heywinit wrote: post #313
madduci wrote: post #302

Have they "squatted" the name? It's the same name for the digital Sovereignty initiative in Germany https://opencode.de/

you'll be surprised the name was actually a controversy on x/twitter since opencode was originally another dev's idea who joined the charmcli team. they wanted to keep that name but dax somehow (?) ended up squatting it. the charmcli team has renamed their tool to "crush" which matches their other tools a lot better than "opencode"

oh yea that whole drama turned me off from this project. dax guy seems to be some sort of grumpy cat.

Re: OpenCode – Open source AI coding agent

#419

Post by DrewADesign »

integralid wrote: post #275
heavyset_go wrote: post #258

Earlier quoted context omitted.

It also sends all of your prompts to Grok's free tier by default, and the free tier trains on your submitted information, X AI can do whatever they want with that, including building ad profiles, etc. You need to set an explicit "small model" in OpenCode to disable that.

This. I work on projects that warrant a self hosted model to ensure nothing is leaked to the cloud. Imagine my surprise when I discovered that even though the only configured model is local, all my prompts are sent to the cloud to... generate a session title. Fortunately caught during testing phase.

I’m curious if there’s a reason you’re not just coding in a container without access to the internet, or some similar setup? If I was worried about things in my dev chain accessing any cloud service, I’d be worried about IDE plugins, libraries included in imports, etc. and probably not want internet access at all.

Re: OpenCode – Open source AI coding agent

#420

Post by embedding-shape »

anonyggs wrote: post #418

I don’t know why people use opencode. I mean it’s better than copilot but it’s pretty terrible in general when there are better options available.

Rather than listing what tooling you think is worse than OpenCode, wouldn't it make sense to list what tooling you think is better?
Post reply on HN